paper-with-me

Papers

Equivariant MuZero

2023-02-09 · Andreea Deac, Théophane Weber, George Papamakarios

Deep reinforcement learning repeatedly succeeds in closed, well-defined domains such as games (Chess, Go, StarCraft). The next frontier is real-world scenarios, where setups are numerous and varied. For this, agents need to learn the underlying rules governing the environment, so as to robustly generalise to conditions that differ from those they were trained on. Model-based reinforcement learning algorithms, such as the highly successful MuZero, aim to accomplish this by learning a world model. However, leveraging a world model has not consistently shown greater generalisation capabilities compared to model-free alternatives. In this work, we propose improving the data efficiency and generalisation capabilities of MuZero by explicitly incorporating the symmetries of the environment in its world-model architecture. We prove that, so long as the neural networks used by MuZero are equivariant to a particular symmetry group acting on the environment, the entirety of MuZero's action-selection algorithm will also be equivariant to that group. We evaluate Equivariant MuZero on procedurally-generated MiniPacman and on Chaser from the ProcGen suite: training on a set of mazes, and then testing on unseen rotated versions, demonstrating the benefits of equivariance. Further, we verify that our performance improvements hold even when only some of the components of Equivariant MuZero obey strict equivariance, which highlights the robustness of our construction.

📄 PDF Abstract BibTeX arXiv:2302.04798

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Starcraft

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
Monte-Carlo Tree Search Monte-Carlo Tree Search is a planning algorithm that accumulates value estimates obtained from Monte Carlo simulations in order to successively direct simulations towards more…
Average Pooling 설명 없음
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Prioritized Experience Replay Prioritized Experience Replay is a type of experience replay in reinforcement learning where we more frequently replay…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Interpreting the Learned Model in MuZero Planning

2024-11-07 · Hung Guei, Yan-Ru Ju, Wei-Yu Chen, Ti-Rong Wu

MuZero has achieved superhuman performance in various games by using a dynamics network to predict environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics netw…

Atari GamesBoard Gamesmodel

What model does MuZero learn?

2023-06-01 · Jinke He, Thomas M. Moerland, Joery A. de Vries, Frans A. Oliehoek

Model-based reinforcement learning (MBRL) has drawn considerable interest in recent years, given its promise to improve sample efficiency. Moreover, when using deep-learned models, it is possible to learn compact and gen…

modelModel-based Reinforcement Learningreinforcement-learningReinforcement Learning

Playing Nondeterministic Games through Planning with a Learned Model

2021-01-01 · Thomas Willkens, Jordan Pollack

The MuZero algorithm is known for achieving high-level performance on traditional zero-sum two-player games of perfect information such as chess, Go, and shogi, as well as visual, non-zero sum, single-player environments…

Visualizing MuZero Models

2021-02-25 · ICML Workshop URL 2021 7 · Joery A. de Vries, Ken S. Voskuil, Thomas M. Moerland, Aske Plaat

MuZero, a model-based reinforcement learning algorithm that uses a value equivalent dynamics model, achieved state-of-the-art performance in Chess, Shogi and the game of Go. In contrast to standard forward dynamics model…

Game of GoModel-based Reinforcement Learning

MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games

2023-10-17 · Ti-Rong Wu, Hung Guei, Pei-Chiun Peng, Po-Wei Huang 외

This paper presents MiniZero, a zero-knowledge learning framework that supports four state-of-the-art algorithms, including AlphaZero, MuZero, Gumbel AlphaZero, and Gumbel MuZero. While these algorithms have demonstrated…

Atari GamesBoard Games